Scholarlink

<p>Fires in postpartum care centers pose significant risks to the safety of mothers and newborns, highlighting the need for effective egress safety evaluation. This study proposes a systematic method for assessing egress safety based on the Egress Safety Ratio in postpartum care center buildings. Fire simulations were conducted to analyze the correlation between fire environment factors (e.g., temperature, toxic gases) and available safe egress time, which served as the foundation for constructing a comprehensive database. Using this database, an artificial neural network-based real-time prediction model was developed, enabling the identification of safe egress routes under various fire scenarios. Additionally, an integrated system for quantitatively evaluating Egress Safety Ratio was established. The reliability of the proposed model was validated by comparing fire simulation results with artificial neural network-based predictions using different postpartum care center floor plans, demonstrating good agreement and confirming its accuracy and effectiveness in evaluating and improving egress safety. The proposed model is expected to serve as a valuable tool for enhancing fire safety in postpartum care centers.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development of an artificial neural network–based egress model incorporating the egress safety ratio under fire in postpartum care center buildings

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月18日

查看全文
  • Khaliunaa Darkhanbat,
  • Amina Erdenebaatar,
  • Inwook Heo,
  • Seung-Ho Choi,
  • Hoseong Jeong,
  • Kang Su Kim

摘要

Fires in postpartum care centers pose significant risks to the safety of mothers and newborns, highlighting the need for effective egress safety evaluation. This study proposes a systematic method for assessing egress safety based on the Egress Safety Ratio in postpartum care center buildings. Fire simulations were conducted to analyze the correlation between fire environment factors (e.g., temperature, toxic gases) and available safe egress time, which served as the foundation for constructing a comprehensive database. Using this database, an artificial neural network-based real-time prediction model was developed, enabling the identification of safe egress routes under various fire scenarios. Additionally, an integrated system for quantitatively evaluating Egress Safety Ratio was established. The reliability of the proposed model was validated by comparing fire simulation results with artificial neural network-based predictions using different postpartum care center floor plans, demonstrating good agreement and confirming its accuracy and effectiveness in evaluating and improving egress safety. The proposed model is expected to serve as a valuable tool for enhancing fire safety in postpartum care centers.